Skip to content

[codex] Make GTM Agent brief-native#2

Open
a3fckx wants to merge 2 commits into
mainfrom
codex/brief-native-gtm-artifacts
Open

[codex] Make GTM Agent brief-native#2
a3fckx wants to merge 2 commits into
mainfrom
codex/brief-native-gtm-artifacts

Conversation

@a3fckx
Copy link
Copy Markdown
Collaborator

@a3fckx a3fckx commented May 11, 2026

What changed

  • Removed the committed campaigns/memory-store-first-gtm campaign workspace from the plugin repo.
  • Added brief-operating-surface.md to make the GTM Agent contract explicit: briefs are current operating truth, recall retrieves evidence, records carry confirmed learning/events, and local files are temporary execution ledgers.
  • Updated GTM Agent and campaign setup skills to produce an approved operating profile first, record approved policy to Memory Store, and create local files only for import/export, review queues, or explicit handoff.
  • Renamed the old campaign-folder guidance in-place to an execution workspace model and updated README, installation docs, Exa setup docs, and eval fixtures to match.

Why

The previous PR made the Memory Store brief contract stronger, but the committed first-campaign folder made the repo look like one static campaign artifact instead of a reusable GTM engineering system. Briefs should now be the product surface; campaign files should be optional runtime/workspace material.

Validation

  • python3 -m json.tool plugins/gtm-agent/evals/memory-contract-checks.json >/dev/null
  • python3 -m json.tool plugins/gtm-agent/evals/skill-routing-cases.json >/dev/null
  • python3 plugins/gtm-agent/scripts/validate_skill_surface.py
  • python3 plugins/gtm-agent/skills/campaign-setup/scripts/test_render_gtm_plan_template.py
  • git diff --check
  • git diff --cached --check
  • node /Users/a3fckx/.codex/plugins/cache/openai-curated/plugin-eval/63976030/scripts/plugin-eval.js analyze plugins/gtm-agent --format markdown

Notes

Plugin Eval still reports GTM Agent as 72/C because the overall deferred reference surface is heavy (deferred_cost_tokens around 44.5k). This PR reduces repo artifact bloat by 1,518 net lines, but it does not attempt the larger reference-budget refactor.


Open in Stage

@stage-review
Copy link
Copy Markdown

stage-review Bot commented May 11, 2026

@a3fckx a3fckx marked this pull request as ready for review May 11, 2026 04:28
Final state of julep-ai/mem-plugins before plugin set migrates to
MemoryStore/plugins. Includes brief-native GTM Agent rewrite, refreshed
Memory Store basics/LinkedIn Studio/Marketplace Operator skills, new
operating + install reproduction docs, and updated marketplace metadata.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant